Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226255887> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4226255887 abstract "Speech emotion recognition (SER) processes speech signals to detect and characterize expressed perceived emotions. Many SER application systems often acquire and transmit speech data collected at the client-side to remote cloud platforms for inference and decision making. However, speech data carry rich information not only about emotions conveyed in vocal expressions, but also other sensitive demographic traits such as gender, age and language background. Consequently, it is desirable for SER systems to have the ability to classify emotion constructs while preventing unintended/improper inferences of sensitive and demographic information. Federated learning (FL) is a distributed machine learning paradigm that coordinates clients to train a model collaboratively without sharing their local data. This training approach appears secure and can improve privacy for SER. However, recent works have demonstrated that FL approaches are still vulnerable to various privacy attacks like reconstruction attacks and membership inference attacks. Although most of these have focused on computer vision applications, such information leakages exist in the SER systems trained using the FL technique. To assess the information leakage of SER systems trained using FL, we propose an attribute inference attack framework that infers sensitive attribute information of the clients from shared gradients or model parameters, corresponding to the FedSGD and the FedAvg training algorithms, respectively. As a use case, we empirically evaluate our approach for predicting the client's gender information using three SER benchmark datasets: IEMOCAP, CREMA-D, and MSP-Improv. We show that the attribute inference attack is achievable for SER systems trained using FL. We further identify that most information leakage possibly comes from the first layer in the SER model." @default.
- W4226255887 created "2022-05-05" @default.
- W4226255887 creator A5010028928 @default.
- W4226255887 creator A5018033573 @default.
- W4226255887 creator A5059832680 @default.
- W4226255887 creator A5070386139 @default.
- W4226255887 creator A5072711823 @default.
- W4226255887 date "2021-12-26" @default.
- W4226255887 modified "2023-09-26" @default.
- W4226255887 title "Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings" @default.
- W4226255887 doi "https://doi.org/10.48550/arxiv.2112.13416" @default.
- W4226255887 hasPublicationYear "2021" @default.
- W4226255887 type Work @default.
- W4226255887 citedByCount "0" @default.
- W4226255887 crossrefType "posted-content" @default.
- W4226255887 hasAuthorship W4226255887A5010028928 @default.
- W4226255887 hasAuthorship W4226255887A5018033573 @default.
- W4226255887 hasAuthorship W4226255887A5059832680 @default.
- W4226255887 hasAuthorship W4226255887A5070386139 @default.
- W4226255887 hasAuthorship W4226255887A5072711823 @default.
- W4226255887 hasBestOaLocation W42262558871 @default.
- W4226255887 hasConcept C119857082 @default.
- W4226255887 hasConcept C13280743 @default.
- W4226255887 hasConcept C154945302 @default.
- W4226255887 hasConcept C185798385 @default.
- W4226255887 hasConcept C204321447 @default.
- W4226255887 hasConcept C205649164 @default.
- W4226255887 hasConcept C2776214188 @default.
- W4226255887 hasConcept C2777438025 @default.
- W4226255887 hasConcept C2779201187 @default.
- W4226255887 hasConcept C28490314 @default.
- W4226255887 hasConcept C38652104 @default.
- W4226255887 hasConcept C41008148 @default.
- W4226255887 hasConceptScore W4226255887C119857082 @default.
- W4226255887 hasConceptScore W4226255887C13280743 @default.
- W4226255887 hasConceptScore W4226255887C154945302 @default.
- W4226255887 hasConceptScore W4226255887C185798385 @default.
- W4226255887 hasConceptScore W4226255887C204321447 @default.
- W4226255887 hasConceptScore W4226255887C205649164 @default.
- W4226255887 hasConceptScore W4226255887C2776214188 @default.
- W4226255887 hasConceptScore W4226255887C2777438025 @default.
- W4226255887 hasConceptScore W4226255887C2779201187 @default.
- W4226255887 hasConceptScore W4226255887C28490314 @default.
- W4226255887 hasConceptScore W4226255887C38652104 @default.
- W4226255887 hasConceptScore W4226255887C41008148 @default.
- W4226255887 hasLocation W42262558871 @default.
- W4226255887 hasOpenAccess W4226255887 @default.
- W4226255887 hasPrimaryLocation W42262558871 @default.
- W4226255887 hasRelatedWork W1485630101 @default.
- W4226255887 hasRelatedWork W2070338563 @default.
- W4226255887 hasRelatedWork W2312116756 @default.
- W4226255887 hasRelatedWork W2498017833 @default.
- W4226255887 hasRelatedWork W2903389359 @default.
- W4226255887 hasRelatedWork W3104224589 @default.
- W4226255887 hasRelatedWork W3139398652 @default.
- W4226255887 hasRelatedWork W4200202829 @default.
- W4226255887 hasRelatedWork W4226255887 @default.
- W4226255887 hasRelatedWork W4287872046 @default.
- W4226255887 isParatext "false" @default.
- W4226255887 isRetracted "false" @default.
- W4226255887 workType "article" @default.